{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:57:04Z","timestamp":1776884224092,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889461","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Xin","family":"Qi","sequence":"first","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyu","family":"Qiang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxing","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent,AI Lab,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuchen","family":"Shi","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaopeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuankun","family":"Xie","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefei","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanjun","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Science,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-469"},{"key":"ref6","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref10","article-title":"Naturalspeech 2: Latent diffusion models are natural and zeroshot speech and singing synthesizers","author":"Shen","year":"2023"},{"key":"ref11","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746690"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref15","article-title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","author":"Lee","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref17","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.30420\/456164010"},{"key":"ref19","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref20","article-title":"Ditto-tts: Efficient and scalable zero-shot text-to-speech with diffusion transformer","author":"Lee","year":"2024"},{"key":"ref21","article-title":"Dex-tts: Diffusion-based expressive text-to-speech with style modeling on time variability","author":"Park","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IALP63756.2024.10661192"},{"key":"ref23","article-title":"Mel-fullsubnet: Mel-spectrogram enhancement for improving both speech quality and asr","author":"Zhou","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10626859"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389748"},{"key":"ref26","article-title":"Cmelgan: An efficient conditional generative model based on mel spectrograms","author":"Qian","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref28","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref29","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref31","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"International conference on machine learning","author":"Rezende"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889461.pdf?arnumber=10889461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:24Z","timestamp":1774416324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889461","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}